Protein Surface 'Fingerprints' Enable De Novo Protein Interaction Design

A computational framework for designing novel protein binders that uses the features of protein surfaces that drive protein-protein interactions (PPIs) is presented in Nature this week. Physical interactions between proteins are essential for most biological processes and much progress has been made in the design of de novo PPIs for biomedical and translational applications. However, designing novel protein binders against specific targets remains a challenge, particularly when no structural elements from pre-existing binders is known. In the new study, a team led by scientists from the École Polytechnique Fédérale de Lausanne developed a geometric deep-learning framework that analyzes protein surfaces to generate "fingerprints" that reflect the geometric and chemical features critical to PPIs. To demonstrate the approach, the researchers computationally designed several de novo protein binders to engage four protein targets including SARS-CoV-2 spike. "Several designs were experimentally optimized, whereas others were generated purely in silico, reaching nanomolar affinity with structural and mutational characterization showing highly accurate predictions," they write. "We anticipate that this conceptual framework for the generation of rich descriptors of molecular surfaces can open possibilities in other important biotechnological fields such as drug design, biosensing, or biomaterials, in addition to providing a means to study interaction networks in biological processes at the systems levels."